Borrowing it
Nothing to install: this file belongs to jack4862/mimo-vision-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jack4862/mimo-vision-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/jack4862/mimo-vision-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/jack4862/mimo-vision-mcp/claude-md)<a href="https://agentmods.dev/instructions/jack4862/mimo-vision-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jack4862/mimo-vision-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01359 | $0.01359 |
| Opus 5 | $0.00679 | $0.00679 |
| Sonnet 5 | $0.00272 | $0.00272 |
| Haiku 4.5 | $0.00136 | $0.00136 |
Grade A, and why
mimo-vision-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
项目概览
mimo-vision-mcp 是一个 MCP Server:用小米 MiMo v2.5 多模态模型,为纯文本主模型(如 deepseek-v4-flash)补齐图像识别。主模型遇到图片时调用本 Server 的工具,Server 读图转 base64 调 MiMo OpenAI 兼容接口,返回纯文本描述。
常用命令
uv sync --dev # 安装依赖(含 dev/pytest)
uv run python server.py # 启动 Server(stdio 传输,阻塞等待)
uv run --env-file .env pytest # 跑全部测试(离线 + 集成)
uv run --env-file .env pytest tests/test_image_utils.py -k test_too_large # 单个测试
uv run --env-file .env pytest tests/test_api.py # 真实 MiMo API 集成测试(无 key 自动 skip)
注册到 Claude Code(全局 user scope;--env-file 与 claude mcp add 不兼容,必须用 -e 显式传 env):
claude mcp add mimo-vision -s user `
-e "MIMO_API_KEY=<key>" -e "MIMO_BASE_URL=https://api.xiaomimimo.com/v1" `
-e "MIMO_VISION_MODEL=mimo-v2.5" -e "MIMO_MAX_TOKENS=2048" `
"$PWD\.venv\Scripts\python.exe" "$PWD\server.py"
配置:复制 .env.example 为 .env 填 MIMO_API_KEY。普通 Key(sk-)走 https://api.xiaomimimo.com/v1;Token Plan(tp-)需把 MIMO_BASE_URL 改为 https://token-plan-cn.xiaomimimo.com/v1。视觉模型必须用 mimo-v2.5(mimo-v2.5-pro 是纯文本)。
架构
数据流:主模型 → MCP 工具(server.py)→ api_client.MimoClient.prepare_image() 读图 → POST /chat/completions → 文本返回。
四模块分层(每层职责单一,勿交叉):
- config.py — 环境变量 →
Configfrozen dataclass;MIMO_API_KEY必填(缺失时中文报错,不泄漏 token)。入口处load_dotenv()保证本地直接运行时也能读.env。 - api_client.py — 唯一发 HTTP 的层。
MimoClient(httpx async、Authorization: Bearer、指数退避重试、错误映射为MimoError);build_vision_message()构造视觉消息;prepare_image()调 image_utils。 - image_utils.py — 图片输入归一化:本地路径 / http(s) URL(下载转 base64,不透传任意 URL 给官方)/ file:// / data URL →
data:image/...;base64,...;格式白名单 + 10MB 校验 + 魔数兜底。 - server.py — FastMCP 实例 + 4 工具(
describe_image/analyze_images/extract_text_from_image/read_image_info)+ 1 资源(mimo://config)。工具层不直接碰 httpx。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 61 lines · 1,359 tokens per session scan A c4d2af8f916e
mimo-vision-mcp CLAUDE.md is an instructions file published in the GitHub repository jack4862/mimo-vision-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,359 tokens to every session, about $0.0068 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.